Convolutional Neural Network Based Virtual Screening

Selecting Machine-Learning Scoring Functions for Structure-Based Virtual Screening

10.26434/chemrxiv.12967160 ◽

2020 ◽

Author(s):

Pedro Ballester

Keyword(s):

Machine Learning ◽

Drug Discovery ◽

Virtual Screening ◽

Predictive Accuracy ◽

Scoring Function ◽

3D Models ◽

Large Datasets ◽

Scoring Functions ◽

Discovery Process ◽

Drug Discovery Process

Interest in docking technologies has grown parallel to the ever increasing number and diversity of 3D models for macromolecular therapeutic targets. Structure-Based Virtual Screening (SBVS) aims at leveraging these experimental structures to discover the necessary starting points for the drug discovery process. It is now established that Machine Learning (ML) can strongly enhance the predictive accuracy of scoring functions for SBVS by exploiting large datasets from targets, molecules and their associations. However, with greater choice, the question of which ML-based scoring function is the most suitable for prospective use on a given target has gained importance. Here we analyse two approaches to select an existing scoring function for the target along with a third approach consisting in generating a scoring function tailored to the target. These analyses required discussing the limitations of popular SBVS benchmarks, the alternatives to benchmark scoring functions for SBVS and how to generate them or use them using freely-available software.

Download Full-text

Selecting Machine-Learning Scoring Functions for Structure-Based Virtual Screening

10.26434/chemrxiv.12967160.v1 ◽

2020 ◽

Author(s):

Pedro Ballester

Keyword(s):

Machine Learning ◽

Drug Discovery ◽

Virtual Screening ◽

Predictive Accuracy ◽

Scoring Function ◽

3D Models ◽

Large Datasets ◽

Scoring Functions ◽

Discovery Process ◽

Drug Discovery Process

Interest in docking technologies has grown parallel to the ever increasing number and diversity of 3D models for macromolecular therapeutic targets. Structure-Based Virtual Screening (SBVS) aims at leveraging these experimental structures to discover the necessary starting points for the drug discovery process. It is now established that Machine Learning (ML) can strongly enhance the predictive accuracy of scoring functions for SBVS by exploiting large datasets from targets, molecules and their associations. However, with greater choice, the question of which ML-based scoring function is the most suitable for prospective use on a given target has gained importance. Here we analyse two approaches to select an existing scoring function for the target along with a third approach consisting in generating a scoring function tailored to the target. These analyses required discussing the limitations of popular SBVS benchmarks, the alternatives to benchmark scoring functions for SBVS and how to generate them or use them using freely-available software.

Download Full-text

A Review on Parallel Virtual Screening Softwares for High-Performance Computers

Pharmaceuticals ◽

10.3390/ph15010063 ◽

2022 ◽

Vol 15 (1) ◽

pp. 63

Author(s):

Natarajan Arul Murugan ◽

Artur Podobas ◽

Davide Gadioli ◽

Emanuele Vitali ◽

Gianluca Palermo ◽

...

Keyword(s):

Drug Discovery ◽

Virtual Screening ◽

High Throughput Screening ◽

High Performance ◽

Parallel Implementation ◽

Scoring Function ◽

Scoring Functions ◽

Screening Programs ◽

Lead Compounds ◽

High Performance Computers

Drug discovery is the most expensive, time-demanding, and challenging project in biopharmaceutical companies which aims at the identification and optimization of lead compounds from large-sized chemical libraries. The lead compounds should have high-affinity binding and specificity for a target associated with a disease, and, in addition, they should have favorable pharmacodynamic and pharmacokinetic properties (grouped as ADMET properties). Overall, drug discovery is a multivariable optimization and can be carried out in supercomputers using a reliable scoring function which is a measure of binding affinity or inhibition potential of the drug-like compound. The major problem is that the number of compounds in the chemical spaces is huge, making the computational drug discovery very demanding. However, it is cheaper and less time-consuming when compared to experimental high-throughput screening. As the problem is to find the most stable (global) minima for numerous protein–ligand complexes (on the order of 106 to 1012), the parallel implementation of in silico virtual screening can be exploited to ensure drug discovery in affordable time. In this review, we discuss such implementations of parallelization algorithms in virtual screening programs. The nature of different scoring functions and search algorithms are discussed, together with a performance analysis of several docking softwares ported on high-performance computing architectures.

Download Full-text

Virtual Screening of the Flavonoids Compounds with the SARS-CoV-2 3C-like Protease as the Lead Compounds for the COVID-19

Coronaviruses ◽

10.2174/2666796702666210222105547 ◽

2021 ◽

Vol 02 ◽

Author(s):

Gabriella Patricia Adisurja ◽

Arli Aditya Parkesit

Keyword(s):

Natural Products ◽

Virtual Screening ◽

Specific Binding ◽

Docking Simulation ◽

Screening Methods ◽

Lead Compound ◽

Qsar Analysis ◽

Lead Compounds ◽

Protease Enzyme ◽

Lead Source

: As per the1st of September 2020, the COVID-19 pandemic has reached an unprecedented level of more than 25 million cases with more than 850,000 deaths. Moreover, all the drug candidates are still undergoing testing in clinical trial. In this regard, a breakthrough in drug design is necessary. One strategy to devise lead compounds is leveraging natural products as a lead source. Several companies and research institutes are currently developing anti-SARS-CoV-2 leads from natural products. Flavanoids are well known as a class of antiviral compounds library. The objective of this research is to employ virtual screening methods for obtaining the best lead compounds from the library of flavonoid compounds. This research employed virtual screening methods that comprised of downloading the protein and lead compound structures, QSAR analysis prediction, iterations of molecular docking simulation, and ADME-TOX simulation for toxicity prediction. The QSAR analysis found that the tested compounds have broad-spectrum antiviral activity, and some of them exhibit specific binding to the 3C-like Protease of the Coronavirus. Moreover, juglanin was found as the compound with the most fit binding with the Protease enzyme of SARS-CoV-2. Although most of the tested compounds are deemed toxic by the ADME-Tox test, further research should be conducted to comprehend the most feasible strategy to deliver the drug to the infected lung cells. The juglanin compound is selected as the most fit candidate as the SARS-CoV-2 lead compound in the tested flavonoid samples. However, further research should be conducted to observe the lead delivery method to the cell.

Download Full-text

BEAR, a Novel Virtual Screening Methodology for Drug Discovery

CrossRef Listing of Deleted DOIs ◽

10.1177/1087057110388276 ◽

2010 ◽

Vol 16 (1) ◽

pp. 129-133 ◽

Cited By ~ 23

Author(s):

Gianluca Degliesposti ◽

Corinne Portioli ◽

Marco Daniele Parenti ◽

Giulio Rastelli

Keyword(s):

Molecular Dynamics ◽

Drug Discovery ◽

Virtual Screening ◽

Screening Methods ◽

Scoring Functions ◽

Free Energies ◽

Reliable Tool ◽

Biological Target ◽

Binding Free Energies ◽

Screening Technology

BEAR (binding estimation after refinement) is a new virtual screening technology based on the conformational refinement of docking poses through molecular dynamics and prediction of binding free energies using accurate scoring functions. Here, the authors report the results of an extensive benchmark of the BEAR performance in identifying a smaller subset of known inhibitors seeded in a large (1.5 million) database of compounds. BEAR performance proved strikingly better if compared with standard docking screening methods. The validations performed so far showed that BEAR is a reliable tool for drug discovery. It is fast, modular, and automated, and it can be applied to virtual screenings against any biological target with known structure and any database of compounds.

Download Full-text

Machine learning classification can reduce false positives in structure-based virtual screening

10.1101/2020.01.10.902411 ◽

2020 ◽

Cited By ~ 1

Author(s):

Yusuf Adeshina ◽

Eric Deeds ◽

John Karanicolas

Keyword(s):

Virtual Screening ◽

Acetylcholinesterase Inhibitors ◽

General Purpose ◽

Training Dataset ◽

Screening Methods ◽

Scoring Functions ◽

Machine Learning Classification ◽

Biochemical Assays ◽

New Strategy ◽

Boosted Decision Trees

AbstractWith the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery’s search for active chemical matter. Modern virtual screening methods are still, however, plagued with high false positive rates: typically, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays. We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because none of the studies reporting new scoring methods have validated their model prospectively within the same study. Here, we report a new strategy for building a training dataset (D-COID) that aims to generate highly-compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework of gradient-boosted decision trees. In retrospective benchmarks, our new classifier shows outstanding performance relative to other scoring functions. We additionally evaluate the classifier in a prospective context, by screening for new acetylcholinesterase inhibitors. Remarkably, we find that nearly all compounds selected by vScreenML show detectable activity at 50 µM, with 10 of 23 providing greater than 50% inhibition at this concentration. Without any medicinal chemistry optimization, the most potent hit from this initial screen has an IC50 of 280 nM, corresponding to a Ki value of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

Download Full-text

METADOCK: A parallel metaheuristic schema for virtual screening methods

The International Journal of High Performance Computing Applications ◽

10.1177/1094342017697471 ◽

2017 ◽

Vol 32 (6) ◽

pp. 789-803 ◽

Cited By ~ 14

Author(s):

Baldomero Imbernón ◽

José M Cecilia ◽

Horacio Pérez-Sánchez ◽

Domingo Giménez

Keyword(s):

Molecular Docking ◽

Virtual Screening ◽

High Performance ◽

Optimization Technique ◽

Screening Methods ◽

Scoring Functions ◽

Dynamic Assignment ◽

Parallel Metaheuristics ◽

Heterogeneous Architectures ◽

Metaheuristic Methods

Virtual screening through molecular docking can be translated into an optimization problem, which can be tackled with metaheuristic methods. The interaction between two chemical compounds (typically a protein, enzyme or receptor, and a small molecule, or ligand) is calculated by using highly computationally demanding scoring functions that are computed at several binding spots located throughout the protein surface. This paper introduces METADOCK, a novel molecular docking methodology based on parameterized and parallel metaheuristics and designed to leverage heterogeneous computers based on heterogeneous architectures. The application decides the optimization technique at running time by setting a configuration schema. Our proposed solution finds a good workload balance via dynamic assignment of jobs to heterogeneous resources which perform independent metaheuristic executions when computing different molecular interactions required by the scoring functions in use. A cooperative scheduling of jobs optimizes the quality of the solution and the overall performance of the simulation, so opening a new path for further developments of virtual screening methods on high-performance contemporary heterogeneous platforms.

Download Full-text

CompScore: boosting structure-based virtual screening performance by incorporating docking scoring functions components into consensus scoring

10.1101/550590 ◽

2019 ◽

Author(s):

Yunierkis Perez-Castillo ◽

Stellamaris Sotomayor-Burneo ◽

Karina Jimenes-Vargas ◽

Mario Gonzalez-Rodriguez ◽

Maykel Cruz-Monteagudo ◽

...

Keyword(s):

Genetic Algorithms ◽

Virtual Screening ◽

High Performance ◽

Scoring Function ◽

Scoring Functions ◽

Traditional Use ◽

Screening Performance ◽

Consensus Scoring ◽

Improved Performance ◽

Virtual Screening Performance

AbstractConsensus scoring has become a commonly used strategy within structure-based virtual screening (VS) workflows with improved performance compared to those based in a single scoring function. However, no research has been devoted to analyze the worth of docking scoring functions components in consensus scoring. We implemented and tested a method that incorporates docking scoring functions components into the setting of high performance VS workflows. This method uses genetic algorithms for finding the combination of scoring components that maximizes the VS enrichment for any target. Our methodology was validated using a dataset that contains ligands and decoys for 102 targets that has been widely used in VS validation studies. Results show that our approach outperforms other methods for all targets. It also boosts the initial enrichment performance of the traditional use of whole scoring functions in consensus scoring by an average of 45%. CompScore is freely available at: http://bioquimio.udla.edu.ec/compscore/

Download Full-text

Convex-PLR – Revisiting affinity predictions and virtual screening using physics-informed machine learning

10.1101/2021.09.13.460049 ◽

2021 ◽

Author(s):

Maria Kadukova ◽

Vladimir Chupin ◽

Sergei Grudinin

Keyword(s):

Machine Learning ◽

Virtual Screening ◽

Scoring Function ◽

Structural Data ◽

Classification Problem ◽

Substantial Improvement ◽

Screening Tests ◽

Conformational Sampling ◽

Scoring Functions ◽

New Model

AbstractVirtual screening is an essential part of the modern drug design pipeline, which significantly accelerates the discovery of new drug candidates. Structure-based virtual screening involves ligand conformational sampling, which is often followed by re-scoring of docking poses. A great variety of scoring functions have been designed for this purpose. The advent of structural and affinity databases and the progress in machine-learning methods have recently boosted scoring function performance. Nonetheless, the most successful scoring functions are typically designed for specific tasks or systems. All-purpose scoring functions still perform poorly on the virtual screening tests, compared to precision with which they are able to predict co-crystal binding poses. Another limitation is the low interpretability of the heuristics being used.We analyzed scoring functions’ performance in the CASF benchmarks and discovered that the vast majority of them have a strong bias towards predicting larger binding interfaces. This motivated us to develop a physical model with additional entropic terms with the aim of penalizing such a preference. We parameterized the new model using affinity and structural data, solving a classification problem followed by regression. The new model, called Convex-PLR, demonstrated high-quality results on multiple tests and a substantial improvement over its predecessor Convex-PL. Convex-PLR can be used for molecular docking together with VinaCPL, our version of AutoDock Vina, with Convex-PL integrated as a scoring function. Convex-PLR, Convex-PL, and VinaCPL are available at https://team.inria.fr/nano-d/convex-pl/.

Download Full-text

Correlation between Virtual Screening Performance and Binding Site Descriptors of Protein Targets

International Journal of Medicinal Chemistry ◽

10.1155/2018/3829307 ◽

2018 ◽

Vol 2018 ◽

pp. 1-10 ◽

Cited By ~ 3

Author(s):

Jamal Shamsara

Keyword(s):

Virtual Screening ◽

Binding Site ◽

Center Of Mass ◽

Scoring Function ◽

Scoring Functions ◽

Autodock Vina ◽

Protein Targets ◽

Shape Complementarity ◽

Screening Performance ◽

Consensus Scoring

Rescoring is a simple approach that theoretically could improve the original docking results. In this study AutoDock Vina was used as a docked engine and three other scoring functions besides the original scoring function, Vina, as well as their combinations as consensus scoring functions were employed to explore the effect of rescoring on virtual screenings that had been done on diverse targets. Rescoring by DrugScore produces the most number of cases with significant changes in screening power. Thus, the DrugScore results were used to build a simple model based on two binding site descriptors that could predict possible improvement by DrugScore rescoring. Furthermore, generally the screening power of all rescoring approach as well as original AutoDock Vina docking results correlated with the Maximum Theoretical Shape Complementarity (MTSC) and Maximum Distance from Center of Mass and all Alpha spheres (MDCMA). Therefore, it was suggested that, with a more complete set of binding site descriptors, it could be possible to find robust relationship between binding site descriptors and response to certain molecular docking programs and scoring functions. The results could be helpful for future researches aiming to do a virtual screening using AutoDock Vina and/or rescoring using DrugScore.

Download Full-text